Bernstein is an open-source governance layer for AI agents that applies written policies, schedules agent work deterministically, controls approvals, and records verifiable execution history. It is used to coordinate CLI coding agents and other agent workloads, including parallel runs and offline review, while the catalogue entries provide its agent workflows and controls.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/sipyourdrink-ltd/bernstein/claude-mdgit clone --depth 1 https://github.com/sipyourdrink-ltd/bernsteinWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/sipyourdrink-ltd/bernstein/claude-md)<a href="https://agentmods.dev/instructions/sipyourdrink-ltd/bernstein/claude-md"><img src="https://agentmods.dev/badge/instructions/sipyourdrink-ltd/bernstein/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01245 | $0.01245 |
| Opus 5 | $0.00622 | $0.00622 |
| Sonnet 5 | $0.00249 | $0.00249 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
bernstein CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
98% identical to bernstein AGENTS.md — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bernstein - CLAUDE.md
Overview
Bernstein is the open-source governance layer for AI agents. It runs on policy as code: you write the policy - who may do what, what needs approval, what must be recorded - and Bernstein enforces it and produces the verifiable record. A deterministic scheduler - no model in the coordination loop - runs agents in parallel, gates what they produce, and records every step, so a run can be verified after the fact, offline, from the artifacts alone. CLI coding agents work out of the box (Claude Code, Codex, Gemini CLI, and 40+ more), and the same layer governs any agent workload: the deliverable can be a diff, a research report, a dataset, or an audit evidence pack. Air-gap install profile included. Apache-2.0.
Module map
Full per-file map: docs/sdd/module-map.md (generated).
| Package | Purpose / detail |
|---|---|
core/ |
orchestration engine - src/bernstein/core/ |
adapters/ |
CLI agent adapters - src/bernstein/adapters/AGENTS.md |
agents/ |
agent catalog & discovery - src/bernstein/agents/ |
cli/ |
Click CLI - src/bernstein/cli/AGENTS.md |
evolution/ |
self-evolution engine - src/bernstein/evolution/ |
eval/ |
evaluation harness - src/bernstein/eval/ |
plugins/ |
plugin system (pluggy) - src/bernstein/plugins/ |
tui/ |
Textual TUI - src/bernstein/tui/ |
github_app/ |
GitHub App integration - src/bernstein/github_app/ |
mcp/ |
MCP server - src/bernstein/mcp/ |
benchmark/ |
SWE-bench - src/bernstein/benchmark/ |
Directory context files
Per-directory context files for agents working inside a subtree. Each covers: what the directory is for, key files, invariants, and how to test that subtree.
| Path | Covers |
|---|---|
src/bernstein/adapters/AGENTS.md |
CLI agent adapters |
src/bernstein/cli/AGENTS.md |
Click CLI |
src/bernstein/core/lineage/AGENTS.md |
Lineage: artifact provenance |
src/bernstein/core/orchestration/AGENTS.md |
Orchestration engine |
src/bernstein/core/quality/AGENTS.md |
Quality gates and verification |
src/bernstein/core/security/AGENTS.md |
Security: audit chain, identity, policy |
tests/AGENTS.md |
Test suite |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +1 lines · +120 tokens per session 89fb6b1a77f3
- 6d ago First seen · 106 lines · 1,125 tokens per session scan A 0c0af8b27dfb
bernstein CLAUDE.md is an instructions file published in the GitHub repository sipyourdrink-ltd/bernstein (1,099 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,245 tokens to every session, about $0.0062 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to bernstein AGENTS.md, differing in 4 lines, and is treated as a copy.
Other instructions, from other repositories
martin-loop AGENTS.md
AGENTS.md instructions for Keesan12/martin-loop, covering martinloop agent operating rules, repository authority, mandatory internal-first sequence, prohibited actions and required internal health proof.
r0b0bench AGENTS.md
Instructions for r0b0tlab/r0b0bench, covering agents.md — working on / running r0b0bench, what this repo is, systems block (every profile), chat-template control (runtime variable) and hard rules.
leashd CLAUDE.md
Instructions for vmehera123/leashd, covering claude.md, commands, install dependencies, run tests (single file / specific test / all) and run tests with coverage.
warrant AGENTS.md
AGENTS.md instructions for s0fractal/warrant, covering agent & contributor conduct (governance-critical), hard rules and precedent (why this file exists).
matrixscroll CLAUDE.md
Instructions for SSX360/matrixscroll, covering claude.md, voice, name real things, banned words and no em-dashes.
scitex-python CLAUDE.md
Claude Code instructions for scitex-ai/scitex-python, covering workflow orchestration, 1. plan mode default, 2. subagent strategy, 3. self-improvement loop and 4. verification before done.